The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, we propose a new approach to data density estimation based on the total sum of distances from a data point, and the recently introduced Recursive Density Estimation technique. It is suitable for autonomous real-time video analytics problems, and has been specifically designed to be executed very fast; it uses integer-only arithmetic with no divisions and no floating point numbers (no...
In this paper, a new method for segmentation and splitting of touching vaginal bacteria based on super pixel method is proposed. Feature fusion is integrated with kernel-based support vector machine (SVM) for bacteria segmentation. After segmentation by super pixel, the touching bacteria regions are further separated according to the defined effective distance. Finally, the separated bacteria are...
Graphics Processing Units (GPUs) have evolved over the years from being graphics accelerator to scalable coprocessor. We implement an algebraic multigrid solver for three dimensional unstructured grids using GPU. Such a solver has extensive applications in Computational Fluid Dynamics (CFD). Using a combination of vertex coloring, optimized memory representations, multi-grid and improved coarsening...
In this paper we present a way to calculate the fusion of multi-focus images based on the linear combination of a pair of images taken by a digital camera with different levels of focus. For the linear combination, a linear function with spatial coherence is optimized to maximize the sharpness of the merged image. By the complexity and dispersity of the linear system of equations arises, the solution...
In this work, we study one of the major problems in exploring the power of GPUs to accelerate video processing applications: countless frames have to be transferred back and forth between the CPU and GPU. We evaluate four different data transfer approaches currently available on modern GPUs: Standard Allocation, Pinned Memory, Data Stream, and Zero-Copy. Our results show that Data Stream is the most...
To overcome the problem of lacking apparent features, e.g. color or shape, in the process of identifying wheat stripe rust from powdery mildew using computer vision algorithms, a novel directional feature based on Improved Rotation Kernel Transformation (IRKT) is proposed. IRKT can calculate the statistics of the direction distribution of infected leaf images in spatial domain. The statistics calculated...
Gesture recognition has important applications in sign language and human - machine interfaces. In recent years, recognizing dynamic hand gesture using multi-modal data has become an emerging research topic. The problem is challenging due to the complex movements of hands and the limitations of data acquisition. In this work, we present a new approach for recognizing hand gesture using motion history...
For the need of actually combining RGB data and depth input in computer vision research, new RGB-D features for object recognition are proposed. We present six kinds of RGB-D kernel matching functions on kernel view. They have the capability of capturing different RGB-depth cues including position, size, shape and distance. Due to the infinite dimensional character in Gaussian space, it is computationally...
Considering the lower accuracy of existing traffic sign recognition methods, a new traffic sign recognition method using histogram of oriented gradient - support vector machine (HOG-SVM) and grid search (GS) is proposed. First, the histogram of oriented gradient (HOG) is used to extract the characteristics of traffic sign. Then the grid search technique is applied to optimize the parameters of support...
Kernel-based Support Vector Machine (SVM) is widely used in many fields (e.g. image classification) for its good generalization, in which the key factor is to design effective kernel functions based on efficient features. In this paper, we propose a new approach that uses a combination of global and local image features to represent images and learns Support Vector Machine classifier with a new and...
The unsharp masking filter is an efficient and effective algorithm frequently applied in image contrast enhancement applications. The principle is based on sharpening object edges by appending a scaled high-pass version of the image to the original. The quality of the processed image is largely dependent on the characteristics of the high-pass signal and the scaling factor. Thus, optimal choices of...
Face detection is one of the most important parts of biometrics and face analysis science. Numerous methods and algorithms have been developed in recent years; however, there is a sensible gap between the current detection rate and the ideal one yet. In this paper, a novel multi-stage face detection method is proposed which can remarkably detect faces in different images with different illumination...
Due to availability of reliable and low cost devices, range maps (depth maps) are extensively used in many applications. Recent advances in human-computer interaction enabled us to interact with computers in intuitive and friendly way. In this paper, we propose a novel approach for recognizing static hand gestures using depth information captured from Photon Mixing Device (PMD) cameras. We segment...
This paper presents a novel multi-features fusion tracking algorithm based on local kernels learning. Histograms of multiple features are extracted based on sub image patches within the target region, and the features fusion weights are calculated respectively for each patch according to the discriminability of features. It means that the same feature employed in different sub image patches gets different...
Big Data era is characterized by the explosive increase of image files on the Internet, massive image files bring great challenges to storage. It is required not only the storage efficiency of massive image files but also the accuracy and robustness of massive image file management and retrieval. To meet these requirements, distributed image file storage system based on cognition is proposed. According...
The overall method used for determining disparity in a stereo setup is a widely recognized framework consisting of four steps of cost space computation, cost aggregation, disparity selection, and post-processing. In this paper a cost aggregation approach for a typical local disparity estimation method is introduced. The method introduced is built on top of an existing method called Adaptive Support-Weight...
Due to its several algorithms with their fast implementations, background subtraction becomes a very important step in many computer vision and video surveillance systems which assume static cameras. Literature counts a large number of robust background subtraction algorithms which try each to outperform the others in a quantitative and qualitative manner. This competition can sometimes confuse the...
The potential and feasibility of applying the knowledge of supervised learning methods to Chinese traditional painting classification is discussed and evaluated. Data bases of different artists and categories are collected, from which numerical features are extracted describing paintings' color, texture and other characteristic. Two classification approaches aiming to school and artist classification...
The use of low-cost devices for depth estimation, such as Microsoft Kinect, is becoming more and more popular in computer vision research. In this paper, we propose an algorithm for background modeling which exploits this kind of devices to make the background and foreground models more robust to effects such as camouflage and illumination changes. Our algorithm, after a preprocessing stage for aligning...
An efficient algorithm is proposed that enhances the traditional mean-shift color histogram based object tracking approaches. We propose prominent local directional pattern variance (LDPT) that can extract directional texture responses and with color we develop a color-texture histogram representation for the target. Experiments show superior performance that allows target to go under complex environment...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.